Merge pull request #1 from redhat-gpte-devopsautomation/main

Push to master repo

.vscode/settings.json

@@ -1,2 +1,3 @@
 {
+    "asciidoc.antora.enableAntoraSupport": true
 }

content/modules/ROOT/nav.adoc

@@ -18,6 +18,9 @@
 
 * xref:10-signed-commits.adoc[10. Sign Commits via git-sign]
 
-* xref:11-introducing-AI.adoc[11. Introducing AI with LLMs]
+* xref:11-AI-demo-setup.adoc[11. AI with LLMs Demo Setup]
+
+* xref:12-AI-chatbot-flow.adoc[12. AI with LLMs Chatbot Flow]
+
+* xref:13-AI-model-exploration.adoc[13. AI Model Exploration]
 
-* xref:99-tips.adoc[99. Tips]

content/modules/ROOT/pages/01-agenda.adoc

@@ -24,7 +24,10 @@
 
 == 10. Signed commits via git-sign
 
-== 11. Introducing AI with LLMs
+== 11. AI with LLMs Demo Setup
 
+== 12. AI with LLMs Chatbot Flow
+
+== 13. AI Model Exploration
 
 

content/modules/ROOT/pages/02-introduction.adoc

@@ -1,14 +1,15 @@
 == Introduction
 
-Red Hat Trusted Application Pipeline
+Red Hat Trusted Application Pipeline and Red Hat OpenShift AI
 
 This demonstration takes the audience on a journey across the Software Development Lifecycle (SDLC), from code, to build, through continuous deployment and finally to running in production. An end-to-end DevSecOps CI/CD demonstration of Red Hat Trusted Application Pipeline (RHTAP) incorporating Developer Hub, a developer self-service portal based on Backstage, to standardize and expedite developer onboarding with golden path templates imbued with security guardrails.
 
-RHTAP = RHDH (developer self-service) + RHTAS (signature, attestation) + RHTPA (SBOM)
+In addition to the SDLC is also the MDLC (Model Development Lifecycle) where LLMs are served/managed by Red Hat OpenShift AI.  These LLMs are then woven into an application.  Offering self-service capabilities for Coders and Modelers. 
 
 Featured products in this demonstration include:
 
 * Red Hat Trusted Application Pipeline
+* Red Hat OpenShift AI
 * Red Hat Developer Hub
 * Red Hat Trusted Artifact Signer
 * Red Hat Trusted Profile Analyzer
@@ -19,6 +20,8 @@ Featured products in this demonstration include:
 * Red Hat OpenShift Dev Spaces
 * Red Hat OpenShift
 
+RHTAP = RHDH (developer self-service) + RHTAS (signature, attestation) + RHTPA (SBOM)
+
 Within a large enterprise the time required for a newly hired app developer to become productive is often measured in weeks.  In this demonstration, we are going to show you how to shrink those weeks down to minutes with a developer-optimized, self-service, Internal Development Platform (IDP) that pre-integrates software supply chain security practices from the moment of project inception.
 
 This is the story of how Red Hat imbues your software supply chain with the content, templates, signatures, attestations, and SBOMs that accelerate your custom application development across the software development lifcycle of code, build, deploy and run.  This is the story of how Red Hat empowers your Platform Engineering teams who then in turn super charge your custom application developers.
@@ -51,7 +54,7 @@ Consider the following steps *BEFORE* sharing your screen with the audience.  Th
 * Previously tested a Dev Space or
 * Double check your local laptop git, mvn and IDE (VS Code, IntelliJ) are ready to go
 
-A super short video on the https://www.youtube.com/watch?v=n1IrNe5MmZg[core value propositions] of *Backstage*
+A super short video on the https://www.youtube.com/watch?v=n1IrNe5MmZg[core value propositions] of *Backstage*.
 
 == Login as developer 
 

content/modules/ROOT/pages/11-AI-demo-setup.adoc

@@ -0,0 +1,107 @@
+== AI with LLMs Demo Setup
+
+In this module we will show you the *setup* steps, the things you do BEFORE going on stage,  and introduce you to a new template that provisions both the SDLC (Software Development Lifecycle) and the MDLC (Model Development Lifecycle). Where the SDLC is implemented as a Tekton-based Trusted Application Pipeline as seen in previous modules and the MDLC is implemented as a Red Hat OpenShift AI (RHOAI) pipeline based on Kubeflow. 
+
+Where RHOAI is responsible for the LLM serving, management, and monitoring.  
+
+Where RHTAP + RHDH is responsible for the application code pipeline and lifecycle.  
+
+A 10-minute video that walks through a AI/ML template for building out a LLM-powered Chatbot https://www.youtube.com/watch?v=4YS0wuUpfAo[chatbot]
+
+image::chatbot-1.png[Chatbot1, width=640, height=480]
+
+image::chatbot-2.png[Chatbot2, width=640, height=480]
+
+A https://www.youtube.com/watch?v=9R1yRNHFpGU[behind the scenes tour] and deeper dive video.
+
+And a video that describes some of the https://youtu.be/0d2JpeqPg3U[clean up process]
+
+
+=== Setup
+
+LLMs take a fair bit of time to "spawn" within their pod, use the cooking show technique by running the template once *BEFORE* taking the stage, before sharing your screen. 
+
+image::LLM-templates.png[]
+
+The primary template to run is called *Secured Chatbot with a Self-Hosted Large Language Model (LLM)*. The best way to learn about this template is to execute it. 
+
+Start a new project, an application that leverages a LLM for Natural Language Processing (NLP).  The creation of a net new LLM-infused microservice is as simple as clicking *Choose* on the *Secured Chatbot with a Self-Hosted Large Language Model (LLM)* template.  
+
+Fill-in some fields and follow the wizard:
+
+Name: *marketingbot*
+
+Group Id: *redhat.janus*
+
+Artifact Id: *marketingbot*
+
+Java Package Name: *org.redhat.janus*
+
+Description: *A LLM infused marketingbot app*
+
+image::chatbot-3.png[]
+
+Click *Next*
+
+Model Name: *parasol-instruct*
+
+image::chatbot-4.png[]
+
+Note: Expanding the list of model names in the screenshot will be covered later, for now, just pick the one you have access to which is *parasol-instruct* out-of-the-box.
+
+Click *Next*
+
+For Image Registry, keep all the defaults
+
+image::chatbot-5.png[]
+
+Click *Next*
+
+For Repository Location, keep all the defaults
+
+image::chatbot-6.png[]
+
+Click *Review*
+
+image::chatbot-7.png[]
+
+Click *Create*
+
+The animation takes few seconds however this hides the heavy lifting happening under the covers.
+
+image::chatbot-8.png[]
+
+Click on *Open Component in catalog*
+
+image::chatbot-9.png[]
+
+Click on *CD* tab
+
+image::chatbot-10.png[]
+
+Look for *Healthy* under the *-ai-build* application
+
+Click on the *Overview tab* and then *RHOAI Data Science Project*
+
+image::chatbot-11.png[]
+
+Login in via *rhsso* and the provided password
+
+Look at the *Deployed Models* section, it is very likely that you do not yet have a green check mark indicating that the model server is in fact up.  It can take several minutes for the model server to be ready.
+
+image::chatbot-12.png[]
+
+The green check mark is important.  Again, use the cooking show technique and "pull the baked cake out of the oven".
+
+image::chatbot-13.png[]
+
+Now, you are ready to begin the basic demo flow. 
+
+
+
+
+
+
+
+
+